You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
" <img src=\"https://i.ibb.co/xfJbPmL/github.png\" height=\"70px\" style=\"padding-bottom:5px;\" />View Source on GitHub</a></td>\n",
@@ -941,51 +941,30 @@
941
941
"id": "HgVvcrYmSKGG"
942
942
},
943
943
"source": [
944
-
"## 2.7 Experiment and **get awarded for the best songs**!!\n",
944
+
"## 2.7 Experiment and **get awarded for the best songs**!\n",
945
945
"\n",
946
946
"Congrats on making your first sequence model in TensorFlow! It's a pretty big accomplishment, and hopefully you have some sweet tunes to show for it.\n",
947
947
"\n",
948
-
"If you want to go further, try to optimize your model and submit your best song! Tweet us at [@MITDeepLearning](https://twitter.com/MITDeepLearning) or [email us](mailto:[email protected]) a copy of the song (if you don't have Twitter), and we'll give out prizes to our favorites! \n",
949
-
"\n",
950
948
"Consider how you may improve your model and what seems to be most important in terms of performance. Here are some ideas to get you started:\n",
951
949
"\n",
952
950
"* How does the number of training epochs affect the performance?\n",
953
951
"* What if you alter or augment the dataset? \n",
954
952
"* Does the choice of start string significantly affect the result? \n",
955
953
"\n",
956
-
"Have fun and happy listening!\n",
954
+
"Try to optimize your model and submit your best song! **MIT students and affiliates will be eligible for prizes during the IAP offering**. To enter the competition, please [email us](mailto:[email protected]) with your name and the following:\n",
957
955
"\n",
956
+
"* a recording of your song;\n",
957
+
"* Jupyter notebook with the code you used to generate the song;\n",
958
+
"* a description and/or diagram of the architecture and hyperparameters you used -- if there are any additional or interesting modifications you made to the template code, please include these in your description.\n",
"You can also tweet us at [@MITDeepLearning](https://twitter.com/MITDeepLearning) a copy of the song! See this example song generated by a previous 6.S191 student (credit Ana Heart): <a href=\"https://twitter.com/AnaWhatever16/status/1263092914680410112?s=20\">song from May 20, 2020.</a></blockquote> \n",
0 commit comments